def sim_NDregion(shape,lineshapes,params,amps):
"""
Simulate a arbitrary dimensional region with one or more peaks.
Parameters:
* shape tuple of region shape
* lineshapes List of lineshapes by label (str) or a lineshape class.
See fit_NDregion for additional documentation.
* params P-length list (P is the number of peaks in region) of
N-length lists of tuples where each each tuple is
lineshape parameters for a given peak and dimension.
* amps P-length of peak amplitudes.
Returns: array containing simulated region
"""
# parse the user-friendly input into a format digestable by s_NDregion
# parse the shape
ndim = len(shape)
# parse the lineshape parameters
if len(lineshapes) != ndim:
raise ValueError("Incorrect number of lineshapes provided")
ls_classes = []
for l in lineshapes:
if type(l) is str:
ls_classes.append(ls_str2class(l))
else:
ls_classes.append(l)
# determind the number of parameters in each dimension.
dim_nparam = [c.nparam(l) for l,c in zip(shape,ls_classes)]
# parse the params parameter
n_peaks = len(params)
p = []
for i,param in enumerate(params):
if len(param) != ndim:
err = "Incorrect number of parameters for peak %i"
raise ValueError(err%(i))
for j,dim_param in enumerate(param):
if len(dim_param) != dim_nparam[j]:
err = "Incorrect number of parameters in peak %i dimension %i"
raise ValueError(err%(i,j))
for g in dim_param:
p.append(g)
# parse the amps parameter
if len(amps) != n_peaks:
raise ValueError("Incorrect number of amplitudes provided")
p = list(amps) + p # amplitudes appended to front of p
# DEBUGGING
#print "p",p
#print "shape",shape
#print "ls_classes",ls_classes
#print "n_peaks",n_peaks
return s_NDregion(p,shape,ls_classes,n_peaks)
def fit_spectrum(spectrum,lineshapes,params,amps,bounds,ampbounds,centers,
rIDs,box_width,error_flag,verb=True,**kw):
"""
Fit a spectrum by region which contain one or more peaks.
Parameters:
* spectrum Slicable spectral data.
* lineshape List of lineshapes by label (str) or a lineshape class.
See fit_NDregion for details.
* params P-length list (P is the number of peaks in region) of
N-length lists of tuples where each each tuple is the
optimiztion starting parameters for a given peak and
dimension lineshape.
* amps P-length list of amplitudes.
* bounds List of bounds for parameter of same shape as params. If
none of the parameters in a given dimension have limits
None can be used, otherwise each dimension should have a
list/tuple of (min,max) or None for each parameter.
min or max may be None when there is no bound in a given
direction.
* ampbounds P-length list of bounds for the amplitude with format
similar to bounds.
* centers List of N-tuples indicating peak centers.
* rIDs P-length list of region numbers (peak with the same
region number are fit together).
* box_width N-tuple indicating box width to add and subtract from
peak centers to form region around peak to fit.
* error_flag Set to True to estimate errors for each lineshape
parameter and amplitude.
* verb Set to True to print summary of each region fit, False
supresses all printing.
* kw Additional keywords passed to the scipy.optimize.leastsq
function.
Returns: param_best,amp_best,iers if error_flag is False
param_best,amp_best,param_err,amp_err,iers if error_flag is True
* params_best Optimal values for lineshape parameters with same format
as params input parameter.
* amp_best List of optimal peak amplitudes.
* param_err Estimated lineshape parameter errors with same format
as oarans inout parameter. (Optional)
* amp_err Estimated peak amplitude errors.
* iers List of interger flag from scipy.optimize.leastsq
indicating if the solution was found for a given peak.
1,2,3,4 indicates that a solution was found. Other indicate
an error.
"""
pbest = [[]]*len(params)
pbest_err = [[]]*len(params)
abest = [[]]*len(params)
abest_err = [[]]*len(params)
iers = [[]]*len(params)
shape = spectrum.shape
ls_classes = []
for l in lineshapes:
if type(l) is str:
ls_classes.append(ls_str2class(l))
else:
ls_classes.append(l)
cIDs = set(rIDs) # region values to loop over
for cID in cIDs:
cpeaks = [i for i,v in enumerate(rIDs) if v==cID]
# select the parameter
cparams = [params[i] for i in cpeaks]
camps = [amps[i] for i in cpeaks]
cbounds = [bounds[i] for i in cpeaks]
campbounds = [ampbounds[i] for i in cpeaks]
ccenters = [centers[i] for i in cpeaks]
# find the box edges
bcenters = np.round(np.array(ccenters).astype('int'))
bmin = bcenters-box_width
bmax = bcenters+box_width+1
# correct for spectrum edges
for i in range(len(shape)):
bmin[:,i][np.where(bmin[:,i] < 0) ] = 0
for i,v in enumerate(shape):
bmax[:,i][np.where(bmax[:,i] > v)] = v
# find the region limits
rmin = edge = np.array(bmin).min(0)
rmax = np.array(bmax).max(0)
# cut the spectrum
s = tuple([slice(mn,mx) for mn,mx in zip(rmin,rmax)])
region = spectrum[s]
# add edge to the box limits
ebmin = bmin - edge
ebmax = bmax - edge
# create the weight mask array
wmask = np.zeros(region.shape,dtype='bool')
for bmn,bmx in zip(ebmin,ebmax):
s = tuple([slice(mn,mx) for mn,mx in zip(bmn,bmx)])
wmask[s] = True
# add edges to the initial parameters
ecparams = [ [ ls.add_edge(p,(mn,mx)) for ls,mn,mx,p in
zip(ls_classes,rmin,rmax,g)] for g in cparams ]
# TODO make this better...
ecbounds = [ [ zip(*[ls.add_edge(b,(mn,mx)) for b in zip(*db)])
for ls,mn,mx,db in zip(ls_classes,rmin,rmax,pb) ]
for pb in cbounds ]
# fit the region
t = fit_NDregion(region,ls_classes,ecparams,camps,ecbounds,campbounds,
wmask,error_flag,**kw)
if error_flag:
ecpbest,acbest,ecpbest_err,acbest_err,ier
cpbest_err = [ [ ls.remove_edge(p,(mn,mx)) for ls,mn,mx,p in
zip(ls_classes,rmin,rmax,g)] for g in ecpbest_err]
else:
ecpbest,acbest,ier = t
# remove edges from best fit parameters
cpbest = [ [ ls.remove_edge(p,(mn,mx)) for ls,mn,mx,p in
zip(ls_classes,rmin,rmax,g)] for g in ecpbest]
if verb:
print "-----------------------"
print "cID:",cID,"ier:",ier,"Peaks fit",cpeaks
print "fit parameters:",cpbest
print "fit amplitudes",acbest
for i,pb,ab in zip(cpeaks,cpbest,acbest):
pbest[i]=pb
abest[i]=ab
iers[i] = ier
if error_flag:
for i,pb,ab in zip(cpeaks,cpbest_err,acbest_err):
pbest_err[i]=pb
abest_err[i]=ab
if error_flag==False:
return pbest,abest,iers
return pbest,abest,pbest_err,abest_err,iers
def fit_NDregion(region,lineshapes,params,amps,bounds=None,
ampbounds=None,wmask=None,error_flag=False,**kw):
"""
Fit a N-dimensional region.
Parameters:
* region N-dimensional region to fit.
* lineshapes List of lineshapes by label (str) or a lineshape class.
* params P-length list (P is the number of peaks in region) of
N-length lists of tuples where each each tuple is the
optimiztion starting parameters for a given peak and
dimension lineshape.
* amps P-length list of amplitudes.
* bounds List of bounds for parameter of same shape as params. If
none of the parameters in a given dimension have limits
None can be used, otherwise each dimension should have a
list/tuple of (min,max) or None for each parameter.
min or max may be None when there is no bound in a given
direction.
* ampbounds P-length list of bounds for the amplitude with format
similar to bounds.
* wmask Array with same shape as region which is used to weight
points in the err calculation, typically a boolean array
is used to exclude certain points in the region. Default
of None will include all points in the region equally
in the error calculation.
* error_flag Set to True to estimate errors for each lineshape
parameter and amplitude.
* kw Additional keywords passed to the scipy.optimize.leastsq
function.
Returns: param_best,amp_best,ier if error_flag is False
param_best,amp_best,param_err,amp_err,ier if error_flag is True
* params_best Optimal values for lineshape parameters with same format
as params input parameter.
* amp_best List of optimal peak amplitudes.
* param_err Estimated lineshape parameter errors with same format
as oarans inout parameter. (Optional)
* amp_err Estimated peak amplitude errors.
* ier Interger flag from scipy.optimize.leastsq indicating if
the solution was found. 1,2,3,4 indicates that a solution
was found. Otherwise the solution was not found.
Note on the lineshape parameter:
Elements of the lineshape parameter list can be string indicating the
lineshape of given dimension or an instance of a lineshape class
which provide a sim method which takes two arguments, the first being the
length of the lineshape the second being a list of lineshape parameters,
and returns a simulated lineshape as well as a nparam method which when
given the length of lineshape returns the number of parameters needed to
describe the lineshape. Currently the following strings are allowed:
* 'g' or 'gauss' Gaussian (normal) lineshape.
* 'l' or 'lorentz' Lorentzian lineshape.
* 'v' or 'voigt' Voigt lineshape.
* 'pv' or 'pvoight' Pseudo Voigt lineshape
* 's' or 'scale' Scaled lineshape.
The first four lineshapes (Gaussian, Lorentzian, Voigt and Pseudo Voigt)
all take a FWHM scale parameter.
The following are all valid lineshapes parameters for a 2D Gaussian peak:
['g','g']
['gauss','gauss']
[ng.lineshapes1d.gauss(),ng.lineshapes1d.gauss()]
"""
# this function parses the user-friendly input into a format digestable
# by f_NDregion, performs the fitting, then format the fitting results
# into a user friendly format
# parse the region parameter
ndim = region.ndim
shape = region.shape
# parse the lineshape parameter
if len(lineshapes) != ndim:
raise ValueError("Incorrect number of lineshapes provided")
ls_classes = []
for l in lineshapes:
if type(l) is str:
ls_classes.append(ls_str2class(l))
else:
ls_classes.append(l)
# determind the number of parameter in each dimension
dim_nparam = [c.nparam(l) for l,c in zip(shape,ls_classes)]
# parse params
n_peaks = len(params)
p0 = []
for i,guess in enumerate(params): # peak loop
if len(guess) != ndim:
err = "Incorrect number of params for peak %i"
raise ValueError(err%(i))
for j,dim_guess in enumerate(guess): # dimension loop
if len(dim_guess) != dim_nparam[j]:
err = "Incorrect number of parameters in peak %i dimension %i"
raise ValueError(err%(i,j))
for g in dim_guess: # parameter loop
p0.append(g)
# parse the bounds parameter
if bounds == None: # No bounds
peak_bounds = [[(None,None)]*i for i in dim_nparam]
bounds = [peak_bounds]*n_peaks
if len(bounds) != n_peaks:
raise ("Incorrect number of parameter bounds provided")
# build the parameter bound list to be passed to f_NDregion
p_bounds = []
for i,peak_bounds in enumerate(bounds): # peak loop
if peak_bounds == None:
peak_bounds = [[(None,None)]*i for i in dim_nparam]
if len(peak_bounds) != ndim:
err = "Incorrect number of bounds for peak %i"
raise ValueError(err%(i))
for j,dim_bounds in enumerate(peak_bounds): # dimension loop
if dim_bounds == None:
dim_bounds = [(None,None)]*dim_nparam[j]
if len(dim_bounds) != dim_nparam[j]:
err = "Incorrect number of bounds for peak %i dimension %i"
raise ValueError(err%(i,j))
for k,b in enumerate(dim_bounds): # parameter loop
if b == None:
b = (None,None)
if len(b) != 2:
err = "No min/max for peak %i dim %i parameter %i"
raise ValueError(err%(i,j,k))
p_bounds.append(b)
# parse amps parameter
if len(amps) != n_peaks:
raise ValueError("Incorrect number of amplitude guesses provided")
p0 = list(amps) + p0 # amplitudes appended to front of p0
# parse ampbounds parameter
if ampbounds == None:
ampbounds = [(None,None)]*n_peaks
if len(ampbounds) != n_peaks:
raise ValueError("Incorrect number of amplitude bounds")
to_add = []
for k,b in enumerate(ampbounds):
if b == None:
b = (None,None)
if len(b) != 2:
err = "No min/max for amplitude bound %i"
raise ValueError(err%(k))
to_add.append(b)
p_bounds = to_add + p_bounds # amplitude bound at front of p_bounds
# parse the wmask parameter
if wmask == None: # default is to include all points in region
wmask = np.ones(shape,dtype='bool')
if wmask.shape != shape:
err = "wmask has incorrect shape:"+str(wmask.shape)+ \
" should be "+str(shape)
raise ValueError(err)
# DEBUGGING
#print "--------------------------------"
#print region
#print ls_classes
#print p0
#print p_bounds
#print n_peaks
#print dim_nparam
#print "================================="
#for i,j in zip(p0,p_bounds):
# print i,j
# include full_output=True when errors requested
if error_flag:
kw["full_output"] = True
# perform fitting
r = f_NDregion(region,ls_classes,p0,p_bounds,n_peaks,wmask,**kw)
# DEBUGGING
#print r
# unpack results depending of if full output requested
if "full_output" in kw and kw["full_output"]:
p_best,cov_xi,infodic,mesg,ier = r
else:
p_best,ier = r
# unpack and repack p_best
# pull off the ampltides
amp_best = p_best[:n_peaks]
# split the remaining parameters into n_peaks equal sized lists
p_list = split_list(list(p_best[n_peaks:]),n_peaks)
# for each peak repack the flat parameter lists to reference by dimension
param_best = [make_slist(l,dim_nparam) for l in p_list]
# return as is if no errors requested
if error_flag==False:
return param_best,amp_best,ier
# calculate errors
p_err = calc_errors(region,ls_classes,p_best,cov_xi,n_peaks)
# unpack and repack the error p_err
# pull off the amplitude errors
amp_err = p_err[:n_peaks]
# split the remaining errors into n_peaks equal sized lists
pe_list = split_list(list(p_err[n_peaks:]),n_peaks)
# for each peak repack the flat errors list to reference by dimension
param_err = [make_slist(l,dim_nparam) for l in pe_list]
return param_best,amp_best,param_err,amp_err,ier
def pick(data,pthres,nthres=None,msep=None,algorithm='connected',
est_params=True,lineshapes=None,edge=None,diag=False,c_struc=None,
c_ndil=0,cluster=True,table=True,axis_names=['A','Z','Y','X']):
"""
Pick (find) peaks in a spectral region.
Parameters:
* data N-dimensional array to pick peaks in.
* pthres Minimum peak height for positive peaks. Set to None to not
detect positive peaks.
* nthres Minimum peak height for negative peaks (typically a
negative value). Set to None to not detect negative peaks.
* msep N-tuple of minimum peak seperations along each axis.
Must be defined if algorithm is 'thresh' or 'thresh-fast'
* algorithm Peak picking algorithm to use. Options are 'thres',
'thres-fast', 'downward', or 'connected'
* est_params Set to True to perform a rough estimate of linewidths and
amplitude for all peaks picked. False returns only the
peak locations.
* lineshapes A list of lineshape classes or string shortcuts for each
dimension. If not specified Gaussian type lineshapes with
a FWHM linewidth parameter is assumed in each dimension.
This parameter if only used if est_params is True.
* edge Tuple to add to peak locations representing the edge of a
slices region. None skips this addition.
* diag Set True to consider diagonal points to be touching in
peak finding algorithm and clustering.
* c_struc Structure element to use when applying dilation on segments
before applying clustering algorithm. None will apply
default square structure with connectivity one will be
used.
* c_ndil Number of dilations to perform on segments before applying
clustering algorithm.
* cluster Set True to cluster touching peaks.
* table Set True to return turn a table.
* axis_names List of axis names, the last n will be used for column
name prefixes in table where n is the number of dimensions.
Returns: locations,[cluster_ids,[scales,amps]] or table
* locations
* cluster_ids
* scales
* amps
* table
"""
####################
# Check parameters #
####################
ndim = len(data.shape)
# check msep
if type(msep) == int:
msep = (msep,)
if algorithm in ['thres','thres-fast'] and len(msep) != ndim:
raise ValueError("msep has incorrect length")
# check algorithm
if algorithm not in ['thres','thres-fast','downward','connected']:
raise ValueError('Invalid algorithm %s'%(algorithm))
# check lineshapes
if est_params:
# expand None
if lineshapes == None:
lineshapes = [gauss() for i in range(ndim)]
ls_classes = []
# replace strings
for l in lineshapes:
if type(l) is str:
ls_classes.append(ls_str2class(l))
else:
ls_classes.append(l)
# check that all classes have 2 parameters
for i,ls in enumerate(ls_classes):
if ls.nparam(10) != 2:
s = "Lineshape class %i does not have two parameters"
raise ValueError(s%(i))
if len(ls_classes) != ndim:
raise ValueError("Incorrect number of lineshapes")
if edge!=None and len(edge)!=ndim:
raise ValueError("edge has incorrect length")
#######################
# find positive peaks #
#######################
if pthres==None: # no locations
ploc = []
pseq = []
elif est_params==True: # find locations and segments
if algorithm == 'thres':
ploc,pseg = find_all_thres_fast(data,pthres,msep,True)
elif algorithm == 'thres-fast':
ploc,pseg = find_all_thres_fast(data,pthres,msep,True)
elif algorithm == 'downward':
ploc,pseg = find_all_downward(data,pthres,True,diag)
elif algorithm == 'connected':
ploc,pseg = find_all_connected(data,pthres,True,diag)
else:
raise ValueError('Invalid algorithm %s'%(algorithm))
else: # find only locations
if algorithm == 'thres':
ploc = find_all_thres_fast(data,pthres,msep,False)
elif algorithm == 'thres-fast':
ploc = find_all_thres_fast(data,pthres,msep,False)
elif algorithm == 'downward':
ploc = find_all_downward(data,pthres,False,diag)
elif algorithm == 'connected':
ploc = find_all_connected(data,pthres,False,diag)
else:
raise ValueError('Invalid algorithm %s'%(algorithm))
#######################
# find negative peaks #
#######################
if nthres==None: # no locations
nloc = []
nseg = []
elif est_params==True: # find locations and segments
if algorithm == 'thres':
nloc,nseg = find_all_nthres(data,nthres,msep,True)
elif algorithm == 'thres-fast':
nloc,nseg = find_all_nthres_fast(data,nthres,msep,True)
elif algorithm == 'downward':
nloc,nseg = find_all_upward(data,nthres,True,diag)
elif algorithm == 'connected':
nloc,nseg = find_all_nconnected(data,nthres,True,diag)
else:
raise ValueError('Invalid algorithm %s'%(algorithm))
else: # find only locations
if algorithm == 'thres':
nloc = find_all_nthres(data,nthres,msep,False)
elif algorithm == 'thres-fast':
nloc = find_all_nthres_fast(data,nthres,msep,False)
elif algorithm == 'downward':
nloc = find_all_upward(data,nthres,False,diag)
elif algorithm == 'connected':
nloc = find_all_nconnected(data,nthres,False,diag)
else:
raise ValueError('Invalid algorithm %s'%(algorithm))
# combine the positive and negative peaks
locations = ploc+nloc
#########################################################
# return locations if no parameter estimation requested #
#########################################################
if est_params==False:
if cluster: # find clusters
cluster_ids = clusters(data,locations,pthres,nthres,c_struc,None, c_ndil)
locations = add_edge(locations,edge)
if table:
return pack_table(locations,cluster_ids,axis_names=axis_names)
else:
return locations,cluster_ids
else: # Do not determine clusters
locations = add_edge(locations,edge)
if table:
return pack_table(locations,axis_names=axis_names)
else:
return locations
##################################
# estimate scales and amplitudes #
##################################
seg_slices = pseg+nseg
scales = [[]]*len(locations)
amps = [[]] * len(locations)
#scales = np.zeros(np.array(locations).shape,dtype=float)
#amps = np.zeros(len(locations),dtype=float)
for i,(l,seg_slice) in enumerate(zip(locations,seg_slices)):
null,scales[i],amps[i]=guess_params_slice(data,l,seg_slice,ls_classes)
########################################################
# return locations, scales and amplitudes as requested #
########################################################
if cluster:
cluster_ids = clusters(data,locations,pthres,nthres,c_struc,None,c_ndil)
locations = add_edge(locations,edge)
if table:
return pack_table(locations,cluster_ids,scales,amps,axis_names)
else:
return locations,cluster_ids,scales,amps
else:
locations = add_edge(locations,edge)
if table:
return pack_table(locations,scales=scales,amps=amps,
axis_names=axis_names)
else:
return locations,scales,amps
